Models / OpenAI / o4-mini

OpenAI · o-mini

o4-mini

Fast o-series model for compact reasoning, coding, and tool use

$1.10 in · $4.40 out

per 1M tokens · first-party price. Reference price from OpenAI, the lab's own listing.

Provider input prices run from $1.10 to $2.00 per 1M tokens. Output prices run from $4.40 to $8.00.

Context
200,000
Max output
100,000
Cache read
$0.28
Cache write
—
Reasoning
Yes
Tool calls
Yes
Structured output
Yes
Vision
Yes
Open weights
No
License
—
Released
Apr 16, 2025
Updated in source
Apr 16, 2025
Knowledge
2024-05
Providers
19

What this model costs per month

Prices are USD per 1M tokens. A month is 30 days. Cache hits use the cache-read rate when the model has one; otherwise the cache field is ignored.

Estimated monthly cost

o4-mini

$13.20

monthly = requests/day × 30 × (input tokens × (1 − cache hit) × input price + input tokens × cache hit × cache-read price + output tokens × output price) ÷ 1,000,000

Providers

Base rates from Models.dev. One row per provider.
ProviderInputOutputCache readCache writeStatus
Abacus$1.10$4.40———
AIHubMix$1.10$4.40$0.28——
Azure$1.10$4.40$0.28—deprecated
Azure Cognitive Services$1.10$4.40$0.28—deprecated
Cloudflare AI Gateway$1.10$4.40$0.28——
DevPass$1.10$4.40$0.28——
Eden AI$1.10$4.40$0.28——
Impossibl$1.10$4.40$0.28——
Kilo Gateway$1.10$4.40$0.28——
LLM Gateway$1.10$4.40$0.28——
Merge Gateway$1.10$4.40$0.28——
NanoGPT$1.10$4.40$0.55——
NEAR AI Cloud$1.10$4.40$0.28——
OpenAIreference$1.10$4.40$0.28—deprecated
OpenRouter$1.10$4.40$0.28——
Requesty$1.21$4.84$0.30——
Vercel AI Gateway$2.00$8.00$0.50——
AnyAPI—————
Model Oracle AI—————

Jobs this model qualifies for